Update RAG_Chatbot_Example.ipynb

Address Jeff's comments

demo_apps/RAG_Chatbot_example/RAG_Chatbot_Example.ipynb

@@ -241,10 +241,8 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
     "model = meta-llama/Llama-2-7b-chat-hf  \n",
     "volume = $PWD/data  \n",
@@ -265,7 +263,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!curl localhost:8080/generate -X POST -H 'Content-Type: application/json' -d '{\"inputs\": \"What is good about Beijing?\", \"parameters\": { \"max_new_tokens\":64}}'     "
+    "!curl localhost:8080/generate -X POST -H 'Content-Type: application/json' -d '{\"inputs\": \"What is good about Beijing?\", \"parameters\": { \"max_new_tokens\":64}}' #Replace the locahost with the IP visible to the machine running the notebook     "
    ]
   },
   {
@@ -290,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -312,7 +310,7 @@
     "DB_FAISS_PATH = 'vectorstore/db_faiss'\n",
     "\n",
     "#Llama2 TGI models host port\n",
-    "LLAMA2_7B_HOSTPORT = \"http://localhost:8080/\"\n",
+    "LLAMA2_7B_HOSTPORT = \"http://localhost:8080/\" #Replace the locahost with the IP visible to the machine running the notebook\n",
     "LLAMA2_13B_HOSTPORT = \"http://localhost:8080/\" #Add your own host ports for model switching. You can host another TGI model on same instance on a different port.\n",
     "\n",
     "\n",
@@ -333,7 +331,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -351,7 +349,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -378,12 +376,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
     "template = \"\"\"\n",
-    "[INST]Use the following pieces of context to answer the question.\n",
+    "[INST]Use the following pieces of context to answer the question. If no context provided, answer like a AI assistant.\n",
     "{context}\n",
     "Question: {question} [/INST]\n",
     "\"\"\"\n",
@@ -402,7 +400,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -445,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -472,7 +470,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -634,9 +632,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://0.0.0.0:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://localhost:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "demo.queue().launch(server_name=\"0.0.0.0\")"
    ]
@@ -649,7 +677,6 @@
     "Once launched, in the notebook or a browser with URL http://0.0.0.0:7860, you should see the UI.  \n",
     "Things to try in the chatbot demo:  \n",
     "* Asking specific questions related to the Llama 2 Getting Started Guide\n",
-    "* Streaming\n",
     "* Adjust parameters such as max new token generated\n",
     "* Switching to another Llama model with another container launched in a separate terminal\n",
     "\n",